You Can Clone Any App for FREE (REA + 9Router) Complete End-to-End Tutorial
This tutorial explains how REA helps an AI agent inspect permitted app behavior and write an original implementation, then shows how to connect Claude Code to free model providers through 9Router. It demonstrates the workflow by building and testing a simplified office suite containing document, spreadsheet, presentation, and drawing tools.
Maitis11 minTranscript found
Quick learning frame
Read this before watching.
Coding-agent workflow is the loop of inspect, route, plan, edit, verify, summarize, and decide what should be automated next.
New playlist item from Maitis; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to reconstruct and validate selected application behavior from permitted inspection while writing an original implementation.
Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.
Concept diagram
Where this video fits.
01Inspect context
02Route tool
03Plan work
04Edit safely
05Verify behavior
06Report next step
Deep lesson
Turn this video into working knowledge.
1,883 cleaned transcript words reviewed across 529 timed caption segments.
Thesis
You Can Clone Any App for FREE (REA + 9Router) Complete End-to-End Tutorial teaches a practical coding-agent workflow move: This tutorial explains how REA helps an AI agent inspect permitted app behavior and write an original implementation, then shows how to connect Claude Code to free model providers through 9Router. It demonstrates the workflow by building and testing a simplified office suite containing document, spreadsheet, presentation, and drawing tools.
The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.
0:16
Reconstruct App Behavior
“literally clone an app or a platform in minutes. And honestly, using it is super simple. You just run one command, then describe what you want in plain English, right inside Claude Code, Codex, or Cursor. Now, I...”
REA does not reveal an application's secret source code; it connects an AI agent to tools such as Ghidra so the agent can study how permitted features behave and write new code that reproduces them. Choose one permitted app feature and write a two-column list separating the visible behavior REA could inspect from the original source code it cannot provide.
3:45
Route Free Models
“Cloud. Click get API key, copy the key, paste it here, and hit test. Then, do the same for open router, Cloudflare, and Gemini. But, here's the catch. Every free model has a limit. Use it a lot...”
9Router sits between Claude Code and multiple model providers, while a combo orders those models and automatically moves to the next one when a free limit is exhausted. The demonstrated setup adds Ollama Cloud, OpenRouter, Cloudflare, Gemini, and Kiro AI before connecting the combo to Claude Code. Sketch the routing chain from Claude Code through 9Router to an ordered five-provider combo, and mark where failover occurs.
7:04
Build Test Improve
“We've got REA connected to Claude code, and I wanted to try something bigger. What if we could rebuild an app millions of people use every day using AI and just one prompt? So, I decided to take...”
After installing only the official `morluto/rea` release and running the doctor preflight, the demonstration builds an original, bounded Office-style workspace rather than attempting every feature at once. It verifies behavior—not just resemblance—by formatting and saving a document, calculating a spreadsheet formula, launching a slideshow, and drawing then saving an image before adding improvements incrementally. Choose one permitted feature, define a functional success test, build the smallest original version, run the test, and request one focused improvement only after it passes.
01
Inspect context
Start with this video's job: This tutorial explains how REA helps an AI agent inspect permitted app behavior and write an original implementation, then shows how to connect Claude Code to free model providers through 9Router. It demonstrates the workflow by building and testing a simplified office suite containing document, spreadsheet, presentation, and drawing tools. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:16, where the video says: “literally clone an app or a platform in minutes. And honestly, using it is super simple. You just run one command, then describe what you want in plain English, right inside Claude Code, Codex, or Cursor. Now, I...”
02
Route tool
Use "Route tool" to locate the part of the coding-agent workflow mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 3:45, where the video says: “Cloud. Click get API key, copy the key, paste it here, and hit test. Then, do the same for open router, Cloudflare, and Gemini. But, here's the catch. Every free model has a limit. Use it a lot...”
03
Plan work
Turn "Plan work" into the reusable artifact for this lesson: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal. This is where watching becomes something you can inspect and reuse.
04
Edit safely
Use "Edit safely" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.
05
Verify behavior
Use "Verify behavior" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.
06
Report next step
Use "Report next step" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed artifact packet
Convert the video into a scoped artifact request that includes the transcript claim, mechanism, acceptance criteria, and proof. The output should be a coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
Example
Coding-agent workflow proof brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the coding-agent workflow pattern.
Example
Teach-back module
Transform the lesson into a definition, a Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step diagram, one misconception, one practice exercise, and a check-for-understanding question.
Do not learn it wrong
Treating the title as the lesson without checking what the transcript actually says.
choosing tools by hype
losing context across agents
letting parallel sessions become invisible
Letting the lesson drift into generic Codex vs Claude comparison.
Letting the lesson drift into feature lists without task routing.
Letting the lesson drift into claims that ignore limits or recovery.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: This tutorial explains how REA helps an AI agent inspect permitted app behavior and write an original implementation, then shows how to connect Claude Code to free model providers through 9Router. It demonstrates the workflow by building and testing a simplified office suite containing document, spreadsheet, presentation, and drawing tools.
02
Explain the practical stakes without hype: New playlist item from Maitis; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
Put it into practice
Give this grounded prompt to Codex or Claude after watching.
You are helping me turn one specific YouTube video into real, durable learning.
Source video:
- Title: You Can Clone Any App for FREE (REA + 9Router) Complete End-to-End Tutorial
- URL: https://www.youtube.com/watch?v=nndv3V5Q7HY
- Topic: Creative Automation
- My current learning frame: On a permitted target, run the official REA preflight, select one bounded behavior, build an original implementation, prove it works with a functional test rather than a screenshot comparison, and add one improvement after the test passes.
- Why this matters: New playlist item from Maitis; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:16 / Evidence 1: "literally clone an app or a platform in minutes. And honestly, using it is super simple. You just run one command, then describe what you want in plain English, right inside Claude Code, Codex, or Cursor. Now, I..."
- 2:09 / Evidence 2: "work alone. It connects your AI to older tools that already existed, like Ghidra, a free tool the NSA released in 2019 that reads a compiled app and shows you what it does. REA just makes those tools..."
- 3:45 / Evidence 3: "Cloud. Click get API key, copy the key, paste it here, and hit test. Then, do the same for open router, Cloudflare, and Gemini. But, here's the catch. Every free model has a limit. Use it a lot..."
- 5:29 / Evidence 4: "E A. Pick Claude Code because that's the agent we just set up. And please don't pick none. If you do, R E A installs, but Claude Code won't even know it's there. If that happens, just run..."
- 7:04 / Evidence 5: "We've got REA connected to Claude code, and I wanted to try something bigger. What if we could rebuild an app millions of people use every day using AI and just one prompt? So, I decided to take..."
- 9:57 / Evidence 6: "software. Maybe there's an app you use every day, but you only need two or three of its features. Instead of building something complicated from scratch, you can use R E A to investigate how those features work,..."
Video-aware target:
- Prompt lane: Coding-agent workflow
- Mechanism to extract: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review.
- Artifact to produce: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
- Artifact must include: task class; agent/tool choice; context packet; verification step; handoff/recovery rule
Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step
- answers to these source questions: What workflow pain is being solved? | What exact coordination mechanism is shown? | What evidence proves it changes the work?
- 3 concrete examples that apply the video idea to real agentic work, such as rate-limit routing; browser verification after a UI edit; long-running /goal session review
- 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: choosing tools by hype; losing context across agents; letting parallel sessions become invisible
- a checklist for the next real workflow, focused on: routing decision, context portability, verification, handoff summary
- one practical exercise with a clear done signal: Route three recent tasks across Codex, Claude, browser checks, and manual review with a reason for each.
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.
Quality bar:
- Make this specific to "You Can Clone Any App for FREE (REA + 9Router) Complete End-to-End Tutorial", not a generic Creative Automation essay.
- Each workflow rule must point to a timestamped claim or demo moment, then state what remains unproven.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: generic Codex vs Claude comparison; feature lists without task routing; claims that ignore limits or recovery.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.
Misconceptions
What to stop believing.
Creative AI removes the need for taste.
It increases the need for taste because output volume explodes.
The best prompt is enough.
References, critique, iteration, and post-production matter just as much.
Practice studio
Learning only counts when you make something.
01
Transcript evidence map
Separate what the video actually says from what you already believe about the topic.
3 source-backed takeaways with timestamps, confidence, and a transfer note.02
One useful artifact
Apply the video to a real workflow and produce a coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
A reusable artifact with a done signal and one verification step.03
Coding-agent workflow teach-back card
Explain the coding-agent workflow mechanism to someone who has not watched the video yet.
A 90-second explanation, one diagram, one example, and one misconception to avoid.
Recall check
Answer first, then reveal — without rewatching.
How does REA help recreate a feature without handing over the original application's source code?
What does a 9Router combo do when the current free model stops working?
What separates a working reconstruction from one that merely resembles the original app?
Source shelf
Use the video as a doorway, then verify with primary sources.
